Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.4406. Min Act: -0.1700
Data Index: 3432317 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.1906. Min Act: -0.1700
Data Index: 1591577 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.1906. Min Act: -0.1700
Data Index: 6823232 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.0656. Min Act: -0.1700
Data Index: 8060324 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.1281. Min Act: -0.1700
Data Index: 5443747 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.0656. Min Act: -0.1700
Data Index: 3887082 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.0656. Min Act: -0.1700
Data Index: 6781910 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.0031. Min Act: -0.1700
Data Index: 8110561 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.0031. Min Act: -0.1700
Data Index: 2170427 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4406. Min Range: -9.4406
Max Act: 9.0656. Min Act: -0.1700
Data Index: 7521280 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.9406. Min Act: -0.1700
Data Index: 294026 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.9406. Min Act: -0.1700
Data Index: 4157633 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.9406. Min Act: -0.1700
Data Index: 793746 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.9406. Min Act: -0.1700
Data Index: 4855872 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.8781. Min Act: -0.1700
Data Index: 1251515 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.8156. Min Act: -0.1700
Data Index: 629353 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.8156. Min Act: -0.1700
Data Index: 3707498 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.8156. Min Act: -0.1700
Data Index: 5327397 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.8156. Min Act: -0.1700
Data Index: 1089507 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4406. Min Range: -9.4406
Max Act: 8.8156. Min Act: -0.1700
Data Index: 1671479 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19